n3world commented on pull request #10662:
URL: https://github.com/apache/arrow/pull/10662#issuecomment-942316179


   > Sorry for not answering earlier; but the degradation looks quite 
concerning indeed. A minor difference (e.g. 3-4%) would be ok, but we seem to 
be getting a 30% slowdown in some of these cases.
   
   I agree that the performance change seems severe. I am not sure why adding 
ints to a second buffer would affect the performance that much. I also was 
getting wildly different values between runs on the same branch sometimes 
almost a 50% change so I am not sure how reliable any of those numbers really 
are. I can play with it some to see if I can figure out what is going on.


-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: [email protected]

For queries about this service, please contact Infrastructure at:
[email protected]


Reply via email to